F24 SALES / MODEL
DeepSeek🇨🇳
DeepSeek V4 Flash
DeepSeek's smaller V4 model combines coding, mathematical reasoning and long-document analysis. It activates 13 billion of 284 billion parameters, with optional thinking for problems that need more than an immediate answer.
Free aggregator routes
These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.
Standard free access requires a balance of at least $5 and shares a daily request allowance; free usage does not consume that balance.
Limits above: Infron. Available gateway routes are listed below.
https://infron.ai/models/deepseek/deepseek-v4-flash:free verifies the undated route, separately from its 0731 listing. The supplied OpenCode entry concerns V4 Flash, but neither listing establishes which revision this Infron alias serves. A separate duplicate_key avoids assuming equivalence with OpenCode, 0731 or V4.1.
Infron
Info- Thinking
- Not documented
deepseek/deepseek-v4-flash:freeModel sources
Use it through LiteLLM
Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.
Download LiteLLM YAML